Lesson 4

Scatterplots and Perceived Audience Size

Notes:

Scatterplots

Notes:

library(tidyverse)

## ── Attaching packages ───────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 2.2.1     ✔ purrr   0.2.4
## ✔ tibble  1.4.2     ✔ dplyr   0.7.4
## ✔ tidyr   0.7.2     ✔ stringr 1.2.0
## ✔ readr   1.1.1     ✔ forcats 0.2.0

## ── Conflicts ──────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

pf<-read.csv('pseudo_facebook.tsv',sep='\t')

ggplot(data=pf,aes(x=age,y=friend_count))+
  geom_point()

ggplot Syntax

Notes:

ggplot(data=pf,aes(x=age,y=friend_count))+
  geom_point()+
  xlim(13,90)

## Warning: Removed 4906 rows containing missing values (geom_point).

Overplotting

Notes:

ggplot(data=pf,aes(x=age,y=friend_count))+
  geom_jitter(alpha=1/20)+
  xlim(13,90)

## Warning: Removed 5173 rows containing missing values (geom_point).

Coord_trans()

Notes:

friendscatter<-ggplot(data=pf,aes(x=age,y=friend_count))+
  geom_point(alpha=1/20,color="orange")+
  xlim(13,90)+
  coord_trans(y="sqrt")
friendscatter

## Warning: Removed 4906 rows containing missing values (geom_point).

Alpha and Jitter

explore the relationship between friends initiated vs. age Notes:

ggplot(data=pf,aes(x=age,y=friendships_initiated))+
  geom_point(alpha=1/20,position=position_jitter(h=0))+
  xlim(13,90)+
  coord_trans(y="sqrt")

## Warning: Removed 5176 rows containing missing values (geom_point).

Overplotting and Domain Knowledge

Notes: friends that see posts makes more sense if you bound as a percentage based on how many total friends they have. ***

Conditional Means

Notes:

# age_groups<-group_by(pf,age)
# pf.fc_by_age<-summarise(age_groups,
#           friend_count_mean=mean(friend_count),
#           friend_count_median=median(friend_count),
#           n=n())
# pf.fc_by_age<-arrange(pf.fc_by_age,age)
# 
# head(pf.fc_by_age)

pf.fc_by_age<- pf%>%
  group_by(age)%>%
  summarise(friend_count_mean=mean(friend_count),
            friend_count_median=median(friend_count),
            n=n())%>%
  arrange(age)

head(pf.fc_by_age)

## # A tibble: 6 x 4
##     age friend_count_mean friend_count_median     n
##   <int>             <dbl>               <dbl> <int>
## 1    13               165                74.0   484
## 2    14               251               132    1925
## 3    15               348               161    2618
## 4    16               352               172    3086
## 5    17               350               156    3283
## 6    18               331               162    5196

Create your plot!

friendline<-ggplot(data=pf.fc_by_age,aes(x=age,y=friend_count_mean))+
  geom_line()
friendline

Overlaying Summaries with Raw Data

Notes:

ggplot(data=pf,aes(x=age,y=friend_count))+
  geom_point(alpha=1/20,color="orange")+
  geom_line(stat="summary",fun.y=mean)+
  geom_line(stat="summary",fun.y=quantile,fun.args=list(probs=.1),
            linetype=2,color="blue")+
  geom_line(stat="summary",fun.y=quantile,fun.args=list(probs=.5),
            color="blue")+
  geom_line(stat="summary",fun.y=quantile,fun.args=list(probs=.9),
            linetype=2,color="blue")+
  coord_cartesian(xlim=c(13,70),ylim=c(0,1000))

#### What are some of your observations of the plot? Response:Note: ggplot 2.0.0 changes the syntax for parameter arguments to functions when using stat = ‘summary’. To denote parameters that are being set on the function specified by fun.y, use the fun.args argument, e.g.:

ggplot( … ) + geom_line(stat = ‘summary’, fun.y = quantile, fun.args = list(probs = .9), … ) To zoom in, the code should use thecoord_cartesian(xlim = c(13, 90)) layer rather than xlim(13, 90) layer.

Look up documentation for coord_cartesian() and quantile() if you’re unfamiliar with them.

Moira: Histogram Summary and Scatterplot

See the Instructor Notes of this video to download Moira’s paper on perceived audience size and to see the final plot.

Notes:

Correlation

Notes:

cor.test(pf$age,pf$friend_count,method="pearson")

## 
##  Pearson's product-moment correlation
## 
## data:  pf$age and pf$friend_count
## t = -8.6268, df = 99001, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.03363072 -0.02118189
## sample estimates:
##         cor 
## -0.02740737

with(pf,cor.test(age,friend_count,method="pearson"))

## 
##  Pearson's product-moment correlation
## 
## data:  age and friend_count
## t = -8.6268, df = 99001, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.03363072 -0.02118189
## sample estimates:
##         cor 
## -0.02740737

Look up the documentation for the cor.test function.

What’s the correlation between age and friend count? Round to three decimal places. Response:

Correlation on Subsets

Notes:

with(subset(pf,age<=70), cor.test(age, friend_count),method='pearson')

## 
##  Pearson's product-moment correlation
## 
## data:  age and friend_count
## t = -52.592, df = 91029, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.1780220 -0.1654129
## sample estimates:
##        cor 
## -0.1717245

Correlation Methods

Notes: The Pearson correlation evaluates the linear relationship between two continuous variables. … The Spearman correlation coefficient is based on the ranked values for each variable rather than the raw data. Spearman correlation is often used to evaluate relationships involving ordinal variables. Pearson is far too sensitive to influential points/outliers for my taste, and while Spearman doesn’t suffer from this problem, I personally find Kendall easier to understand, interpret and explain than Spearman.

If, for example, one variable is the identity of a college basketball program and another variable is the identity of a college football program, one could test for a relationship between the poll rankings of the two types of program: do colleges with a higher-ranked basketball program tend to have a higher-ranked football program? A rank correlation coefficient can measure that relationship, and the measure of significance of the rank correlation coefficient can show whether the measured relationship is small enough to likely be a coincidence.

pearson > normal spearman > robust to outliers ***

Create Scatterplots

Notes:

ggplot(data=pf,aes(x=www_likes_received,y=likes_received))+
  geom_point()+
  coord_trans(x='sqrt',y='sqrt')

ggplot(data=pf,aes(x=www_likes_received,y=likes_received))+
  geom_point()+
  xlim(0,quantile(pf$likes_received,.95))+
  ylim(0,quantile(pf$likes_received,.95))+
  geom_smooth(method ='lm',color='red')

## Warning: Removed 4936 rows containing non-finite values (stat_smooth).

## Warning: Removed 4936 rows containing missing values (geom_point).

## Warning: Removed 31 rows containing missing values (geom_smooth).

with(pf, cor.test(likes_received,www_likes_received,method='pearson'))

## 
##  Pearson's product-moment correlation
## 
## data:  likes_received and www_likes_received
## t = 937.1, df = 99001, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.9473553 0.9486176
## sample estimates:
##       cor 
## 0.9479902

# install.packages('alr3')
library(alr3)

## Loading required package: car

## 
## Attaching package: 'car'

## The following object is masked from 'package:dplyr':
## 
##     recode

## The following object is masked from 'package:purrr':
## 
##     some

data(Mitchell)
?Mitchell

ggplot(data=Mitchell,aes(x=Month,y=Temp))+
  geom_point()

with(Mitchell,cor.test(Month,Temp,method='pearson'))

## 
##  Pearson's product-moment correlation
## 
## data:  Month and Temp
## t = 0.81816, df = 202, p-value = 0.4142
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.08053637  0.19331562
## sample estimates:
##        cor 
## 0.05747063

ggplot(data=Mitchell,aes(x=Month,y=Temp))+
  geom_point()+
  scale_x_continuous(breaks=seq(0,203,12))

p1<-ggplot(data=subset(pf.fc_by_age,age<71),
           aes(x=age,y=friend_count_mean))+
  geom_line()
p1

pf%>%
  mutate(age_with_months=age+(1-dob_month/12))->pf

# pf$age_with_months <- with(pf, age + (1 - dob_month / 12))

pf.fc_by_age_months<- pf%>%
  group_by(age_with_months)%>%
  summarise(friend_count_mean=mean(friend_count),
            friend_count_median=median(friend_count),
            n=n())%>%
  arrange(age_with_months)

p2<-ggplot(data=subset(pf.fc_by_age_months,age_with_months<71),
       aes(x=age_with_months,y=friend_count_mean))+
  geom_line()
p2

library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

grid.arrange(p2,p1,ncol=1)

p1<-p1+geom_smooth()
p2<-p2+geom_smooth()
p3<-ggplot(data=subset(pf,age<71),
           aes(x=round(age/5)*5,y=friend_count))+
  geom_line(stat='summary',fun.y=mean)

grid.arrange(p2,p1,p3,ncol=1)

## `geom_smooth()` using method = 'loess'
## `geom_smooth()` using method = 'loess'